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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <<(
    -0.07
     Credential
    -0.07
     axial
    -0.07
    Campaign
    -0.06
    	mysql
    -0.06
     ctypes
    -0.06
    ‌دهد
    -0.06
     endian
    -0.06
     wrongly
    -0.06
     sf
    -0.06
    POSITIVE LOGITS
     nationals
    0.07
    香
    0.07
     "->
    0.06
    ('</
    0.06
    ivas
    0.06
     sais
    0.06
    _vlog
    0.06
     Analyst
    0.06
    ("")]↵
    0.06
     onto
    0.06
    Act Density 0.085%

    No Known Activations