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

    Neuronpedia

    INDEX
    Explanations

    Negative statements/criticisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oooo
    -0.07
    _LOOK
    -0.07
    Interpolator
    -0.07
    配上
    -0.07
    คล
    -0.07
    为主
    -0.07
     отлича
    -0.07
    .prototype
    -0.07
    大大
    -0.07
     emailed
    -0.07
    POSITIVE LOGITS
    agment
    0.07
    agogue
    0.07
     black
    0.07
    -vesm
    0.06
    holes
    0.06
    vision
    0.06
    ELEMENT
    0.06
    ġ
    0.06
    charges
    0.06
    irms
    0.06
    Act Density 0.007%

    No Known Activations