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

    Neuronpedia

    INDEX
    Explanations

    deep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibir
    -0.06
     impass
    -0.06
     crossings
    -0.06
    RAP
    -0.06
     iterators
    -0.06
     irritated
    -0.06
     motivated
    -0.06
     wires
    -0.06
     angered
    -0.06
    annual
    -0.06
    POSITIVE LOGITS
    [label
    0.07
     obscure
    0.06
     także
    0.06
    .additional
    0.06
    DFS
    0.06
    ($.
    0.06
    を見
    0.06
    .gui
    0.06
     adventurers
    0.06
    .Creator
    0.06
    Act Density 0.004%

    No Known Activations