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

    Neuronpedia

    INDEX
    Explanations

    arm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proprio
    -0.07
     �
    -0.07
    ной
    -0.06
    说
    -0.06
     الولايات
    -0.06
     قسمت
    -0.06
     školy
    -0.06
    FPS
    -0.06
     pohyb
    -0.06
    ционного
    -0.06
    POSITIVE LOGITS
     disarm
    0.12
     dismantle
    0.11
     dismant
    0.09
    Dear
    0.08
     unarmed
    0.07
     prepares
    0.07
    _VM
    0.07
     micron
    0.07
     sincerely
    0.07
    mnt
    0.06
    Act Density 0.002%

    No Known Activations