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

    Neuronpedia

    INDEX
    Explanations

    absorption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choses
    -0.07
     Nep
    -0.07
     Ph
    -0.06
    Upload
    -0.06
     Nile
    -0.06
     alist
    -0.06
     defiance
    -0.06
     값을
    -0.06
     poate
    -0.06
    ecer
    -0.06
    POSITIVE LOGITS
     Ś
    0.06
     absent
    0.06
    ichert
    0.06
     onFailure
    0.06
    	assertFalse
    0.06
     sincerely
    0.06
    _IRQHandler
    0.06
    ภาค
    0.06
    .lon
    0.06
    diff
    0.06
    Act Density 0.006%

    No Known Activations