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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ://
    -1.22
     Advanced
    -1.02
     advanced
    -0.96
    ://"
    -0.89
    Advanced
    -0.87
     advance
    -0.85
     ADVANCED
    -0.80
    advanced
    -0.77
     Advance
    -0.77
    ADVANCED
    -0.70
    POSITIVE LOGITS
    did
    0.66
    SharedCtor
    0.66
    soever
    0.63
     MainAxisSize
    0.63
    Much
    0.62
    MemoryWarning
    0.61
    UnknownFieldSet
    0.60
    iecie
    0.60
    eh
    0.59
    modelBuilder
    0.58
    Act Density 0.130%

    No Known Activations