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

    Neuronpedia

    INDEX
    Explanations

    .local

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incumbent
    -0.08
    Community
    -0.07
    ambled
    -0.07
     council
    -0.07
     sindical
    -0.07
     veteran
    -0.07
    incare
    -0.07
     incumb
    -0.07
    ಿಖ
    -0.07
    Mobile
    -0.07
    POSITIVE LOGITS
     रंग
    0.08
     иг
    0.08
     protagonistas
    0.08
     बीच
    0.08
    .constraints
    0.08
     vetor
    0.07
    عود
    0.07
     weißen
    0.07
     రంగ
    0.07
    عيد
    0.07
    Act Density 0.001%

    No Known Activations