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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     контролю
    -0.07
     plates
    -0.07
     deutschland
    -0.07
    943
    -0.06
     vamos
    -0.06
    irling
    -0.06
    оне
    -0.06
     dvou
    -0.06
    agers
    -0.06
    Require
    -0.06
    POSITIVE LOGITS
     Said
    0.06
     viscosity
    0.06
     abdominal
    0.06
    mention
    0.06
    ")->
    0.06
     lecture
    0.06
    ,ep
    0.06
     Easy
    0.05
     À
    0.05
    سام
    0.05
    Act Density 0.007%

    No Known Activations