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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mid
    -0.07
     budouc
    -0.07
     restrict
    -0.07
    (folder
    -0.07
    لفة
    -0.06
     vốn
    -0.06
     against
    -0.06
     女
    -0.06
    .Options
    -0.06
    ivě
    -0.06
    POSITIVE LOGITS
    алась
    0.06
     зан
    0.06
    їх
    0.06
     Achilles
    0.06
     detach
    0.06
    .Arguments
    0.06
    .enter
    0.06
    229
    0.06
    Ac
    0.06
     Hakk
    0.06
    Act Density 0.001%

    No Known Activations