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

    Neuronpedia

    INDEX
    Explanations

    heterogeneous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (org
    -0.07
     Clifford
    -0.06
    Steven
    -0.06
    Doctrine
    -0.06
    -war
    -0.06
     إن
    -0.05
    14
    -0.05
     способом
    -0.05
     iov
    -0.05
    168
    -0.05
    POSITIVE LOGITS
     Hick
    0.08
     kleine
    0.07
    ável
    0.07
     MCP
    0.07
     Gent
    0.07
    _WEIGHT
    0.07
     ){↵↵
    0.07
     heterogeneous
    0.07
    ژ
    0.07
     Behavior
    0.07
    Act Density 0.005%

    No Known Activations