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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sang
    -0.07
     interest
    -0.07
    ité
    -0.07
     café
    -0.06
     verifies
    -0.06
    uml
    -0.06
    �
    -0.06
     stadium
    -0.06
     scores
    -0.06
     sung
    -0.06
    POSITIVE LOGITS
     PARTICULAR
    0.07
    .insert
    0.07
     लक
    0.06
    _lex
    0.06
     دیده
    0.06
     Erotische
    0.06
    Non
    0.06
    ประเทศไทย
    0.06
    (copy
    0.06
     طر
    0.06
    Act Density 0.005%

    No Known Activations