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

    Neuronpedia

    INDEX
    Explanations

    hold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accident
    -0.07
    $obj
    -0.06
    increase
    -0.06
     believers
    -0.06
     Ма
    -0.06
    ＿＿
    -0.06
     senses
    -0.06
     traverse
    -0.06
     clientes
    -0.06
    pagina
    -0.06
    POSITIVE LOGITS
     charged
    0.07
     emotionally
    0.07
    lfw
    0.07
    럼
    0.06
     Held
    0.06
     hym
    0.06
    achment
    0.06
    propri
    0.06
     Hamas
    0.06
     scrutiny
    0.06
    Act Density 0.005%

    No Known Activations