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

    Neuronpedia

    INDEX
    Explanations

    odes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Basically
    -0.06
     Ced
    -0.06
     �
    -0.06
     actual
    -0.06
    _cl
    -0.06
     MATERIAL
    -0.06
    fg
    -0.06
    .pres
    -0.06
    aviour
    -0.06
     Handbook
    -0.06
    POSITIVE LOGITS
    -register
    0.06
     제
    0.06
    注册
    0.06
    ──
    0.06
    mpz
    0.06
     mekan
    0.06
     guardian
    0.06
     nominated
    0.06
     consist
    0.06
    Upgrade
    0.06
    Act Density 0.000%

    No Known Activations