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

    Neuronpedia

    INDEX
    Explanations

    code, logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("<?
    -0.07
     kişisel
    -0.07
    IRCLE
    -0.07
    (segment
    -0.07
    (receiver
    -0.06
    flat
    -0.06
     아니
    -0.06
     diag
    -0.06
     damp
    -0.06
    (bus
    -0.06
    POSITIVE LOGITS
    ไลน
    0.07
    ات
    0.07
     drib
    0.07
     стара
    0.06
     Cad
    0.06
     cutter
    0.06
     xlink
    0.06
     awards
    0.06
    ात
    0.06
    нов
    0.06
    Act Density 0.029%

    No Known Activations