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

    Neuronpedia

    INDEX
    Explanations

    existing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suites
    -0.08
     dép
    -0.08
    <ll
    -0.08
     dépenses
    -0.07
     batting
    -0.07
     complexion
    -0.07
    ammu
    -0.07
    worm
    -0.07
    gl
    -0.07
    ,min
    -0.07
    POSITIVE LOGITS
     overwrite
    0.13
     overwritten
    0.12
    Overwrite
    0.12
    overwrite
    0.11
     overw
    0.11
     conflict
    0.10
     conflito
    0.10
     Conflict
    0.10
     conflitos
    0.10
    Conflict
    0.10
    Act Density 0.007%

    No Known Activations