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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suck
    -0.08
    block
    -0.07
    Teachers
    -0.07
    ⾔
    -0.07
    -aos
    -0.07
     hasNext
    -0.07
     déjà
    -0.07
    いう
    -0.07
    ча
    -0.07
    初创
    -0.07
    POSITIVE LOGITS
    .intersection
    0.09
    OptionsItemSelected
    0.07
    .raises
    0.07
    lust
    0.07
    stantiateViewController
    0.07
    (Parcel
    0.07
    เทร
    0.06
    	TRACE
    0.06
    lararas
    0.06
    authorized
    0.06
    Act Density 0.002%

    No Known Activations