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

    Neuronpedia

    INDEX
    Explanations

    hatred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (DialogInterface
    -0.06
     CGAffineTransform
    -0.06
     emergency
    -0.06
    だろう
    -0.06
    .drag
    -0.06
    mkdir
    -0.06
     Βροχή
    -0.06
    .Clone
    -0.06
    ('');↵↵
    -0.06
    _flash
    -0.06
    POSITIVE LOGITS
     hatred
    0.08
    500
    0.07
    下去
    0.07
     после
    0.06
     Malaysian
    0.06
     Độ
    0.06
     همچنین
    0.06
     poměrně
    0.06
     #:
    0.06
     within
    0.06
    Act Density 0.015%

    No Known Activations