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

    Neuronpedia

    INDEX
    Explanations

    based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polarization
    -0.06
     Cz
    -0.06
    افر
    -0.06
    andy
    -0.06
     Salesforce
    -0.06
     año
    -0.06
     Halk
    -0.06
    zdy
    -0.06
     Nobel
    -0.06
    CEF
    -0.06
    POSITIVE LOGITS
    _PRIORITY
    0.07
    _algorithm
    0.07
    :[],↵
    0.07
    ),↵
    0.07
    _binding
    0.06
    +.
    0.06
    .Appearance
    0.06
     affecting
    0.06
     marrow
    0.06
    inished
    0.06
    Act Density 0.008%

    No Known Activations