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

    Neuronpedia

    INDEX
    Explanations

    ictive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yesu
    -0.08
     Bedeut
    -0.08
    cred
    -0.08
     ವಿಶ್ವ
    -0.08
     טוב
    -0.07
    絶
    -0.07
     ഇനി
    -0.07
     neighborhoods
    -0.07
    urdy
    -0.07
     definitiv
    -0.07
    POSITIVE LOGITS
     tendencies
    0.10
     tendency
    0.08
    (value
    0.08
    iosity
    0.08
    :value
    0.08
    miss
    0.08
    しています
    0.08
    (Value
    0.08
    ,value
    0.07
    endency
    0.07
    Act Density 0.001%

    No Known Activations