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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (face
    -0.07
    Enumer
    -0.07
     müssen
    -0.06
     malloc
    -0.06
     rend
    -0.06
     apprentice
    -0.06
     sustainable
    -0.06
     Voll
    -0.06
    Perfil
    -0.06
     Rio
    -0.06
    POSITIVE LOGITS
    (clicked
    0.08
     (_.
    0.07
    ="">
↵
    0.06
    utton
    0.06
    period
    0.06
    放
    0.06
     release
    0.06
    -gray
    0.06
     released
    0.06
    KN
    0.06
    Act Density 0.043%

    No Known Activations