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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쪽
    -0.06
    _IR
    -0.06
    _PF
    -0.06
    效果
    -0.06
    KEN
    -0.06
     PIT
    -0.06
     PIN
    -0.06
    \xf
    -0.06
    _rot
    -0.06
     कड
    -0.06
    POSITIVE LOGITS
     Fra
    0.07
     monetary
    0.07
    emphasis
    0.06
     forget
    0.06
     bailout
    0.06
     Instantiate
    0.06
     sanitation
    0.06
     schema
    0.06
     Declarations
    0.06
     полож
    0.06
    Act Density 0.011%

    No Known Activations