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

    Neuronpedia

    INDEX
    Explanations

    early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ради
    -0.07
     infrared
    -0.07
    frared
    -0.07
    89
    -0.07
    flation
    -0.07
    .pro
    -0.07
    _HORIZONTAL
    -0.07
    CADE
    -0.07
    pared
    -0.07
    _cred
    -0.07
    POSITIVE LOGITS
     early
    0.08
     sooner
    0.07
    Oregon
    0.07
    早
    0.07
     newData
    0.07
     timings
    0.06
     соз
    0.06
     сход
    0.06
     sớm
    0.06
     expecting
    0.06
    Act Density 0.023%

    No Known Activations