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
    ats
    -0.07
    政
    -0.06
    .YEAR
    -0.06
     Saw
    -0.06
    dsl
    -0.06
     variance
    -0.06
     Zac
    -0.06
    MMM
    -0.06
     LSTM
    -0.06
    .handleChange
    -0.06
    POSITIVE LOGITS
    Update
    0.07
    ว
    0.06
     Maya
    0.06
     screen
    0.06
     Experimental
    0.06
    adopt
    0.06
     universe
    0.06
     Preparation
    0.06
     labs
    0.06
    ibar
    0.06
    Act Density 0.000%

    No Known Activations