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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ко
    -0.06
     Continuing
    -0.06
     Addition
    -0.06
    ̃
    -0.06
     Getting
    -0.06
    +offset
    -0.06
    eneg
    -0.06
     pursuant
    -0.06
     adj
    -0.06
    _posts
    -0.06
    POSITIVE LOGITS
     insider
    0.07
    лює
    0.07
    .RowStyle
    0.07
    群
    0.07
     CLIIIK
    0.07
     cluster
    0.06
    .sulake
    0.06
    uther
    0.06
    hots
    0.06
     ladies
    0.06
    Act Density 0.001%

    No Known Activations