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

    Neuronpedia

    INDEX
    Explanations

    assumptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meld
    -0.07
    (op
    -0.06
    PP
    -0.06
    oodles
    -0.06
    iš
    -0.06
    альном
    -0.06
     朝
    -0.06
    IPLE
    -0.06
    comes
    -0.06
    unfold
    -0.06
    POSITIVE LOGITS
     Παν
    0.06
    <Token
    0.06
    <Any
    0.06
    :UIButtonTypeCustom
    0.06
    详
    0.06
     مطرح
    0.06
    \Image
    0.06
    WWW
    0.06
    шие
    0.06
     �
    0.06
    Act Density 0.060%

    No Known Activations