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

    Neuronpedia

    INDEX
    Explanations

    Collision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -java
    -0.07
     Pamela
    -0.07
    _Execute
    -0.06
     Cp
    -0.06
     ros
    -0.06
     aerial
    -0.06
     aisle
    -0.06
    _compat
    -0.06
    _tgt
    -0.06
     Steven
    -0.06
    POSITIVE LOGITS
     звичай
    0.07
    conscious
    0.06
    RegExp
    0.06
    .zoom
    0.06
    )—
    0.06
     midi
    0.06
    -offs
    0.06
    持ち
    0.06
     соль
    0.06
     generosity
    0.06
    Act Density 0.004%

    No Known Activations