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

    Neuronpedia

    INDEX
    Explanations

    departing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    をした
    -0.06
     hairst
    -0.06
    ItemSelected
    -0.06
     Ire
    -0.06
     Activation
    -0.06
     Catalyst
    -0.06
    .authorization
    -0.06
     similarity
    -0.06
     satellites
    -0.06
    ’in
    -0.06
    POSITIVE LOGITS
    πα
    0.07
    olf
    0.07
    บาล
    0.07
    SIDE
    0.07
     announcement
    0.06
    =>$
    0.06
     chai
    0.06
     coinc
    0.06
     Shepard
    0.06
    olumn
    0.06
    Act Density 0.040%

    No Known Activations