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

    Neuronpedia

    INDEX
    Explanations

    military

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Belle
    -0.06
     unserem
    -0.06
    _tD
    -0.06
    _dep
    -0.06
    chnitt
    -0.06
    Fat
    -0.06
    affected
    -0.05
     landing
    -0.05
    qn
    -0.05
    (display
    -0.05
    POSITIVE LOGITS
    StringLength
    0.07
    umbotron
    0.07
    .cli
    0.07
     ای
    0.06
    ahaha
    0.06
    ishlist
    0.06
     servant
    0.06
     cropping
    0.06
    compatible
    0.06
     irrit
    0.06
    Act Density 0.018%

    No Known Activations