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
     róż
    -0.07
     şeh
    -0.07
     хоч
    -0.07
     tanggal
    -0.07
     кух
    -0.07
     Chall
    -0.06
    pytest
    -0.06
     cholesterol
    -0.06
     слиз
    -0.06
    survey
    -0.06
    POSITIVE LOGITS
     arm
    0.19
     Arm
    0.18
    Arm
    0.15
     arms
    0.15
     ARM
    0.13
     Arms
    0.12
     armed
    0.11
     Armstrong
    0.11
    arm
    0.10
    _arm
    0.10
    Act Density 0.015%

    No Known Activations