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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ětš
    -0.07
    يق
    -0.06
    eyh
    -0.06
    ikal
    -0.06
    _State
    -0.06
    _Ch
    -0.06
     François
    -0.06
    �
    -0.06
    _cre
    -0.06
    :C
    -0.06
    POSITIVE LOGITS
    直接
    0.07
     Aspen
    0.06
     và
    0.06
     offend
    0.06
    FIRST
    0.06
    Driving
    0.06
    gulp
    0.06
    velte
    0.06
    _set
    0.06
     greens
    0.05
    Act Density 0.000%

    No Known Activations