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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    (tb
    -0.06
    挂
    -0.06
     Cs
    -0.06
     redefine
    -0.06
    ุ
    -0.06
     τελ
    -0.06
     superstar
    -0.06
     cabbage
    -0.06
    145
    -0.06
    POSITIVE LOGITS
    _boost
    0.07
     cavity
    0.07
     selbst
    0.07
    Locations
    0.07
    .hidden
    0.07
    NullException
    0.06
     haystack
    0.06
    emit
    0.06
    _transition
    0.06
    _sequences
    0.06
    Act Density 0.009%

    No Known Activations