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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    対
    -0.06
     spread
    -0.06
     fourth
    -0.06
    What
    -0.06
    inc
    -0.06
    ("-",
    -0.06
     colder
    -0.06
    ceph
    -0.06
     Pride
    -0.06
     Rename
    -0.06
    POSITIVE LOGITS
    вай
    0.06
    _wf
    0.06
    ILLS
    0.06
    	vo
    0.06
     aray
    0.06
     hizo
    0.06
    .blocks
    0.06
    '))->
    0.06
    充
    0.06
     찬
    0.06
    Act Density 0.009%

    No Known Activations