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

    Neuronpedia

    INDEX
    Explanations

    перв/Prime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PERMISSION
    -0.08
     Authorities
    -0.06
    Slim
    -0.06
     institutions
    -0.06
     active
    -0.06
    lambda
    -0.06
    cosa
    -0.06
    device
    -0.06
    builder
    -0.06
    (weight
    -0.06
    POSITIVE LOGITS
     갤로그
    0.07
     ของ
    0.07
    rena
    0.06
    ει
    0.06
    STEM
    0.06
    �n
    0.06
     було
    0.06
    ��
    0.06
    セ
    0.06
    elez
    0.06
    Act Density 0.005%

    No Known Activations