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

    Neuronpedia

    INDEX
    Explanations

    moment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datap
    -0.07
    با
    -0.07
     Astroph
    -0.06
    avar
    -0.06
    ammo
    -0.06
    _F
    -0.06
    Talk
    -0.06
    の方
    -0.06
    _address
    -0.06
    (cookie
    -0.06
    POSITIVE LOGITS
     psychosis
    0.07
    ANTS
    0.07
    getString
    0.07
     walls
    0.06
    Mont
    0.06
    ห
    0.06
     stag
    0.06
    ाक
    0.06
    izon
    0.06
     sole
    0.06
    Act Density 0.004%

    No Known Activations