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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     господар
    -0.07
     enlargement
    -0.06
    ByUsername
    -0.06
     malls
    -0.06
    _for
    -0.06
     व
    -0.06
    iking
    -0.06
    日の
    -0.06
     trab
    -0.06
    158
    -0.06
    POSITIVE LOGITS
    (IF
    0.06
    Recorder
    0.06
     cui
    0.06
    Dump
    0.06
     Jude
    0.06
    .Primary
    0.06
     Replica
    0.06
     masih
    0.06
    Oregon
    0.06
    .worker
    0.06
    Act Density 0.032%

    No Known Activations