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

    Neuronpedia

    INDEX
    Explanations

    ^{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     well
    -0.07
    HL
    -0.06
    』
    -0.06
     عمل
    -0.06
     �
    -0.06
    .…
    -0.06
    adil
    -0.06
    都不
    -0.06
     Panels
    -0.06
     zs
    -0.06
    POSITIVE LOGITS
    ^{
    0.14
     ^{
    0.11
    ata
    0.08
    ала
    0.08
    ^{-
    0.08
    À
    0.07
     Nina
    0.07
    ATA
    0.07
    .A
    0.07
    Mass
    0.07
    Act Density 0.006%

    No Known Activations