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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (",
    -0.08
     него
    -0.07
    _that
    -0.07
    私
    -0.07
     SQL
    -0.06
     corrosion
    -0.06
     oddly
    -0.06
    dict
    -0.06
    输
    -0.06
    Alle
    -0.06
    POSITIVE LOGITS
     conqu
    0.07
    chunk
    0.06
    aphael
    0.06
     EFF
    0.06
     Ability
    0.06
     otur
    0.06
    нулся
    0.06
     ofrece
    0.06
    /resource
    0.06
     pigment
    0.06
    Act Density 0.033%

    No Known Activations