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

    Neuronpedia

    INDEX
    Explanations

    Realization or surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [end
    -0.07
    ivic
    -0.07
     Skate
    -0.07
     itching
    -0.07
    отреб
    -0.06
    ávis
    -0.06
    IPP
    -0.06
     Allan
    -0.06
    Assertion
    -0.06
    .XtraEditors
    -0.06
    POSITIVE LOGITS
     Cour
    0.07
     OH
    0.06
     Feb
    0.06
     gh
    0.06
     Petit
    0.06
     trimest
    0.06
     genes
    0.06
    pkt
    0.06
     ep
    0.06
     cheats
    0.06
    Act Density 0.022%

    No Known Activations