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

    Neuronpedia

    INDEX
    Explanations

    Boiling potatoes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ric
    -0.09
     experience
    -0.08
    协
    -0.08
    experience
    -0.08
     sentiment
    -0.08
     probabilities
    -0.08
     performances
    -0.07
     Weib
    -0.07
     commitment
    -0.07
     in
    -0.07
    POSITIVE LOGITS
    覆盖
    0.13
     couvrir
    0.11
     ঢাকা
    0.11
     нив
    0.11
     хамгийн
    0.10
     najle
    0.10
    opfu
    0.10
     cubrir
    0.10
    覆
    0.10
     ენ
    0.10
    Act Density 0.003%

    No Known Activations