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

    Neuronpedia

    INDEX
    Explanations

    algebra/math expression variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olacak
    -0.06
     tour
    -0.06
    >tag
    -0.06
    Pass
    -0.06
    .Return
    -0.06
    OUSE
    -0.06
     College
    -0.06
     hits
    -0.06
    _F
    -0.06
    ipping
    -0.06
    POSITIVE LOGITS
     neutron
    0.07
     monumental
    0.07
     positional
    0.07
     chrono
    0.07
     Spokane
    0.07
    ỳ
    0.07
     Persona
    0.07
     Armenia
    0.07
    .DIS
    0.07
    eld
    0.06
    Act Density 0.003%

    No Known Activations