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

    Neuronpedia

    INDEX
    Explanations

    pass

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     econ
    -0.07
     methyl
    -0.07
    frican
    -0.06
     league
    -0.06
     Coral
    -0.06
    _ary
    -0.06
     Dread
    -0.06
     tří
    -0.06
     Creating
    -0.06
     rotor
    -0.06
    POSITIVE LOGITS
     pass
    0.12
     Pass
    0.11
     PASS
    0.11
    -pass
    0.10
     passing
    0.10
    Pass
    0.10
     passer
    0.09
    pass
    0.09
     passes
    0.09
     passe
    0.09
    Act Density 0.046%

    No Known Activations