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

    Neuronpedia

    INDEX
    Explanations

    numbers starting with 58

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .removeAll
    -0.07
     '</
    -0.06
     Number
    -0.06
     pickup
    -0.06
    tm
    -0.06
     removeAll
    -0.06
     minced
    -0.06
     Binary
    -0.06
    구글상위
    -0.06
    LM
    -0.06
    POSITIVE LOGITS
    591
    0.11
    58
    0.08
    057
    0.08
    �
    0.08
    595
    0.08
    596
    0.08
    058
    0.07
    585
    0.07
    593
    0.07
    594
    0.07
    Act Density 0.017%

    No Known Activations