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

    Neuronpedia

    INDEX
    Explanations

    regularization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니
    -0.07
    starttime
    -0.06
    .minimum
    -0.06
     lief
    -0.06
    尽
    -0.06
     seam
    -0.06
    หาร
    -0.06
     Matcher
    -0.06
     Semaphore
    -0.06
    CEEDED
    -0.06
    POSITIVE LOGITS
     Particip
    0.08
     teplot
    0.07
     distracting
    0.07
    !");↵↵
    0.07
    ]<<
    0.06
     MIME
    0.06
    ','=','
    0.06
    �
    0.06
    ……」↵↵
    0.06
     disrupted
    0.06
    Act Density 0.005%

    No Known Activations