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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nosis
    -0.09
     induc
    -0.08
     ontology
    -0.08
    .Uri
    -0.08
    Siempre
    -0.08
    Consensus
    -0.07
     consensus
    -0.07
     horny
    -0.07
     functioneren
    -0.07
    .jwt
    -0.07
    POSITIVE LOGITS
     Thousands
    0.09
     Thousand
    0.09
     হাজার
    0.09
     हजार
    0.08
     thousand
    0.08
     thousands
    0.08
     milliers
    0.08
     yaklaşık
    0.08
     Ele
    0.08
     (~
    0.08
    Act Density 0.205%

    No Known Activations