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

    Neuronpedia

    INDEX
    Explanations

    watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    めて
    -0.07
     Caleb
    -0.07
     ().
    -0.07
     rumors
    -0.07
    )].
    -0.06
    abbit
    -0.06
    .fr
    -0.06
    .n
    -0.06
    aired
    -0.06
    _dept
    -0.06
    POSITIVE LOGITS
    (dd
    0.06
    _velocity
    0.06
    125
    0.06
    /App
    0.06
     trä
    0.06
    102
    0.06
    _TP
    0.06
     dishes
    0.06
    UPS
    0.06
    ~-
    0.06
    Act Density 0.000%

    No Known Activations