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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENCIAS
    0.41
    ransom
    0.39
    isible
    0.38
    lesias
    0.38
    ONENTS
    0.38
    ife
    0.37
    arantine
    0.37
     ransom
    0.36
     ident
    0.36
    endorf
    0.36
    POSITIVE LOGITS
     {!
    0.46
    Remy
    0.42
     prof
    0.40
    wyd
    0.39
     Profil
    0.38
     GoPro
    0.38
    炲
    0.38
     debugDocument
    0.38
     duh
    0.37
     发布
    0.37
    Act Density 0.000%

    No Known Activations