Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words with preposition pairings that describe a process or situation

    oai_token-act-pair · gemini-2.0-flash

    diverse or non-English terms

    np_token-act-pair-logits · gpt-4o-mini

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.77
    ंदीखरीदारी
    -0.68
    WriteBarrier
    -0.67
    aarrggbb
    -0.63
    MessageTagHelper
    -0.62
    bigoplus
    -0.60
     kasarigan
    -0.59
     Abonnez
    -0.59
    Reparto
    -0.58
    mybatisplus
    -0.58
    POSITIVE LOGITS
    AddTagHelper
    0.46
    artigen
    0.45
    ക്ഷ
    0.44
    jain
    0.43
    ]")]
    0.42
    Mention
    0.42
     Beauchamp
    0.42
    ტერ
    0.41
     Alter
    0.41
     Biôgrafia
    0.41
    Act Density 1.068%

    No Known Activations