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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Credential
    -0.07
    すぎ
    -0.07
    _flux
    -0.07
     유지
    -0.06
    Ionic
    -0.06
    scalar
    -0.06
    actus
    -0.06
    _:
    -0.06
    DIRECTORY
    -0.06
    .stride
    -0.06
    POSITIVE LOGITS
     pies
    0.06
     س
    0.06
     Providers
    0.06
     Wet
    0.06
    	opts
    0.06
    ryan
    0.06
    gran
    0.06
    _blue
    0.05
     koc
    0.05
     آتش
    0.05
    Act Density 0.027%

    No Known Activations