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

    Neuronpedia

    INDEX
    Explanations

    ANS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cú
    -0.07
    _Post
    -0.07
    툩
    -0.07
    혼
    -0.07
    ally
    -0.07
    毖
    -0.07
    RU
    -0.07
     lacked
    -0.07
     pilot
    -0.07
     adoption
    -0.06
    POSITIVE LOGITS
     JSName
    0.08
    .instrument
    0.08
     annoying
    0.07
     Investig
    0.07
    Iron
    0.07
     anti
    0.07
     eigen
    0.07
    SpinBox
    0.07
     grayscale
    0.07
    -reference
    0.07
    Act Density 0.000%

    No Known Activations