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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <=",
    -0.65
     Curran
    -0.58
     esquecer
    -0.58
     préférence
    -0.54
    addContainerGap
    -0.53
    pero
    -0.53
    Appear
    -0.52
     zosta
    -0.52
     zost
    -0.51
    ceras
    -0.51
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.75
    NamedQueries
    0.60
    >::
    0.57
    RectangleBorder
    0.52
    atasaray
    0.51
    <bos>
    0.48
     afford
    0.47
    bijt
    0.46
     provide
    0.46
     enumerate
    0.46
    Act Density 0.009%

    No Known Activations