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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setw
    -0.06
    		    ↵
    -0.06
    _NORMAL
    -0.06
     Dam
    -0.06
    _IDENTIFIER
    -0.06
    /R
    -0.06
    cedure
    -0.06
     кер
    -0.06
    .ap
    -0.06
    -election
    -0.06
    POSITIVE LOGITS
     Tube
    0.07
     residents
    0.07
     Speaker
    0.07
    haar
    0.06
    rox
    0.06
     Společ
    0.06
     personnel
    0.06
     Ell
    0.06
     Refuge
    0.06
     Perkins
    0.06
    Act Density 0.005%

    No Known Activations