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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memcpy
    -0.08
     cudaMemcpy
    -0.07
     luaL
    -0.07
     malformed
    -0.07
    _dump
    -0.07
    	memcpy
    -0.07
    暧昧
    -0.07
    .scatter
    -0.07
     Intl
    -0.07
     chanting
    -0.07
    POSITIVE LOGITS
    לח
    0.08
    weit
    0.08
     Constraints
    0.07
    Campo
    0.07
    ↦
    0.07
    Hits
    0.07
    ()>
    0.07
    itto
    0.07
    onet
    0.07
    تب
    0.06
    Act Density 0.047%

    No Known Activations