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

    Neuronpedia

    INDEX
    Explanations

    .SH

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     USSR
    -0.08
    .active
    -0.07
    劐
    -0.07
     manned
    -0.07
     Roma
    -0.07
    _accuracy
    -0.07
    (rowIndex
    -0.07
     wysoko
    -0.07
    .getIn
    -0.07
     fires
    -0.06
    POSITIVE LOGITS
     newcomer
    0.07
    aq
    0.07
    kbd
    0.07
    atype
    0.07
     vids
    0.07
    	K
    0.07
     internals
    0.07
     бук
    0.06
    SG
    0.06
    千元
    0.06
    Act Density 0.001%

    No Known Activations