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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fourth
    -0.08
     Fifth
    -0.08
     Conn
    -0.08
     prophetic
    -0.07
     Implementation
    -0.07
     CE
    -0.07
    Thursday
    -0.07
     loser
    -0.07
     Handling
    -0.07
     Robinson
    -0.07
    POSITIVE LOGITS
     بحاجة
    0.08
     interesados
    0.08
     Fahr
    0.08
     interested
    0.08
    wired
    0.08
     inherits
    0.08
     interesado
    0.08
     prov
    0.08
     å
    0.07
     mindful
    0.07
    Act Density 0.097%

    No Known Activations