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

    Neuronpedia

    INDEX
    Explanations

    time management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Means
    -0.06
    促
    -0.06
     Seems
    -0.06
     payloads
    -0.06
     rog
    -0.06
     остав
    -0.06
    พวกเข
    -0.06
     payload
    -0.05
     voir
    -0.05
     Nina
    -0.05
    POSITIVE LOGITS
     linestyle
    0.07
     pasture
    0.06
     Lutheran
    0.06
    opr
    0.06
    _tri
    0.06
    .BL
    0.06
     submar
    0.06
    next
    0.06
    #create
    0.06
    /apis
    0.06
    Act Density 0.050%

    No Known Activations