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

    Neuronpedia

    INDEX
    Explanations

    numbers in research contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %[
    -0.07
    :UIAlert
    -0.07
     tears
    -0.07
    @GetMapping
    -0.07
    جميع
    -0.07
    觑
    -0.07
     assail
    -0.07
    eparator
    -0.06
    _rename
    -0.06
     inoc
    -0.06
    POSITIVE LOGITS
    افي
    0.07
    _Description
    0.07
    关闭
    0.06
    Logo
    0.06
    ppo
    0.06
    units
    0.06
     tanto
    0.06
    常说
    0.06
     Sean
    0.06
    적
    0.06
    Act Density 0.000%

    No Known Activations