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

    Neuronpedia

    INDEX
    Explanations

    contamination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sala
    -0.07
     seat
    -0.07
     Brooks
    -0.07
    resse
    -0.07
     rise
    -0.07
     fds
    -0.07
     wise
    -0.07
     rosa
    -0.07
     河
    -0.06
     της
    -0.06
    POSITIVE LOGITS
     contamination
    0.12
     contaminated
    0.10
     contamin
    0.10
     contaminants
    0.08
    htag
    0.07
    Mix
    0.07
    anyl
    0.07
    _MOUNT
    0.07
    foot
    0.07
    )))
    0.07
    Act Density 0.007%

    No Known Activations