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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividing
    -0.06
    ◆
    -0.06
    Stmt
    -0.06
    메
    -0.06
    &gt
    -0.06
    Oi
    -0.06
    GENCY
    -0.06
    ût
    -0.06
     rid
    -0.06
    顶
    -0.06
    POSITIVE LOGITS
    rove
    0.07
    ecake
    0.07
    (xy
    0.07
     communic
    0.07
     potrav
    0.07
    _Two
    0.07
    (Api
    0.06
     Liu
    0.06
     Ticaret
    0.06
    kova
    0.06
    Act Density 0.000%

    No Known Activations