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

    Neuronpedia

    INDEX
    Explanations

    Location names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touch
    -0.06
     useful
    -0.06
    omething
    -0.06
    …↵↵
    -0.06
    grade
    -0.06
     huge
    -0.06
    iba
    -0.06
    vore
    -0.06
     massive
    -0.06
     Massive
    -0.06
    POSITIVE LOGITS
     Psr
    0.07
    .TabControl
    0.06
    経
    0.06
    	Task
    0.06
     erotici
    0.06
     chol
    0.06
     acompan
    0.06
     compl
    0.06
     Baptist
    0.06
    ｱ
    0.06
    Act Density 0.011%

    No Known Activations