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

    Neuronpedia

    INDEX
    Explanations

    damage, degradation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competency
    -0.07
     smoothly
    -0.07
     Motors
    -0.07
    PV
    -0.07
     CW
    -0.07
    uš
    -0.07
    FU
    -0.07
    mín
    -0.07
     PDO
    -0.07
    orst
    -0.06
    POSITIVE LOGITS
     ${({
    0.07
    Scient
    0.06
    _appro
    0.06
    .align
    0.06
    polygon
    0.06
     <+
    0.06
    。また
    0.06
    �果
    0.06
    /arch
    0.06
    나
    0.06
    Act Density 0.130%

    No Known Activations