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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مُعرِّف
    -0.59
    hamshire
    -0.56
    gorithm
    -0.54
    béco
    -0.53
    sitions
    -0.53
    yship
    -0.52
    paž
    -0.51
    AnchorTagHelper
    -0.50
    ITUD
    -0.49
     signatures
    -0.49
    POSITIVE LOGITS
    ISupport
    0.59
     mild
    0.59
    
    0.57
    <?
    0.56
     inflammation
    0.53
    ResumeLayout
    0.51
    Tikang
    0.50
    WEBPACK
    0.50
    DeleteBehavior
    0.49
    __*/
    0.49
    Act Density 0.004%

    No Known Activations