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

    Neuronpedia

    INDEX
    Explanations

    Reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SYSTEM
    -0.06
    .NUM
    -0.06
     Tab
    -0.06
     ra
    -0.06
     =========================================================================
    -0.06
    Global
    -0.06
     Stage
    -0.06
    ="{!!
    -0.06
     Sparse
    -0.06
     Kremlin
    -0.06
    POSITIVE LOGITS
    #w
    0.07
    biology
    0.07
     knew
    0.07
     slashing
    0.06
    lasting
    0.06
     inertia
    0.06
     booze
    0.06
     poultry
    0.06
    �
    0.06
     Marino
    0.06
    Act Density 0.057%

    No Known Activations