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

    Neuronpedia

    INDEX
    Explanations

    shell scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resi
    -0.08
     synes
    -0.08
    datable
    -0.08
     dais
    -0.08
    builders
    -0.07
     administering
    -0.07
    찮
    -0.07
    ंस
    -0.07
     bedside
    -0.07
     spectacle
    -0.07
    POSITIVE LOGITS
     unset
    0.09
    Unset
    0.08
     Minimum
    0.08
     paranoia
    0.08
    _consts
    0.08
     Defensive
    0.08
     Kann
    0.08
     defensive
    0.07
     Constants
    0.07
     ತುಂಬ
    0.07
    Act Density 0.001%

    No Known Activations