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

    Neuronpedia

    INDEX
    Explanations

    dashes and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .offsetWidth
    -0.06
    ContentAlignment
    -0.06
    �
    -0.06
    .her
    -0.06
    _("
    -0.06
    ух
    -0.06
    Rect
    -0.06
    repositories
    -0.06
     uzak
    -0.06
     الرح
    -0.06
    POSITIVE LOGITS
     composed
    0.07
    概
    0.06
    ческого
    0.06
     carefully
    0.06
     rape
    0.06
     advers
    0.06
     Tra
    0.06
    θα
    0.06
     пут
    0.06
     commencement
    0.06
    Act Density 0.007%

    No Known Activations