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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [at
    -0.06
     erad
    -0.06
     sensors
    -0.06
    *((
    -0.06
    SuppressLint
    -0.06
     byt
    -0.06
     gradually
    -0.06
     ng
    -0.06
     employed
    -0.06
     cambiar
    -0.06
    POSITIVE LOGITS
     πρω
    0.07
     Uph
    0.06
     olmasına
    0.06
    .Fields
    0.06
     Jehovah
    0.06
     sodom
    0.06
     pudd
    0.06
    .fp
    0.06
     ^{}
    0.06
     rampage
    0.06
    Act Density 0.030%

    No Known Activations