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

    Neuronpedia

    INDEX
    Explanations

    Unfortunate situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     american
    -0.07
    phas
    -0.07
    -0.07
     Abb
    -0.06
     Hans
    -0.06
    (runtime
    -0.06
     unclear
    -0.06
     Ear
    -0.06
    aster
    -0.06
    Hope
    -0.06
    POSITIVE LOGITS
     Maint
    0.06
     mutlu
    0.06
    uten
    0.06
    (PyObject
    0.06
    학년
    0.06
    <usize
    0.06
     창
    0.06
    �
    0.06
    ший
    0.06
     mos
    0.06
    Act Density 0.072%

    No Known Activations