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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Punctuation and brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انيف
    -0.48
    izielle
    -0.45
    ExtendWith
    -0.44
     Golden
    -0.44
     Rom
    -0.43
    #+#
    -0.42
    團
    -0.42
    oro
    -0.42
    tvguidetime
    -0.42
    hasData
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.90
     ingår
    0.81
     avoient
    0.78
     étoient
    0.77
     فريبيس
    0.77
     Inscrivez
    0.75
     verksamhet
    0.74
     pouvoit
    0.73
     anún
    0.73
     étoit
    0.71
    Act Density 13.684%

    No Known Activations