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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iddia
    -0.07
     //↵↵
    -0.07
    \Event
    -0.07
    .bank
    -0.06
     sunglasses
    -0.06
     complexes
    -0.06
     demok
    -0.06
     kW
    -0.06
    problem
    -0.06
     автомоб
    -0.06
    POSITIVE LOGITS
    -controlled
    0.06
    REG
    0.06
     EventArgs
    0.06
    ificação
    0.06
     leave
    0.06
    UST
    0.06
     Tahoe
    0.06
    ent
    0.06
    342
    0.06
     Bind
    0.06
    Act Density 0.006%

    No Known Activations