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

    Neuronpedia

    INDEX
    Explanations

    charge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruku
    -0.07
    \u
    -0.06
    dsl
    -0.06
    (_.
    -0.06
    edriver
    -0.06
    ätzlich
    -0.06
     rus
    -0.06
    (note
    -0.06
     Grocery
    -0.06
    ňují
    -0.06
    POSITIVE LOGITS
     vanity
    0.08
    خصص
    0.07
     billed
    0.07
     shout
    0.06
     viv
    0.06
     fortune
    0.06
     Angels
    0.06
     Smarty
    0.06
     Physicians
    0.06
    assertInstanceOf
    0.06
    Act Density 0.000%

    No Known Activations