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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Usage
    -0.07
     mc
    -0.07
     TRANSACTION
    -0.06
    timezone
    -0.06
    lm
    -0.06
     BOOST
    -0.06
    _Tool
    -0.06
    になり
    -0.06
     Bright
    -0.06
     lem
    -0.06
    POSITIVE LOGITS
    {}
    0.07
    �
    0.07
     proficiency
    0.06
    .swift
    0.06
     آنجا
    0.06
     soud
    0.06
     cận
    0.06
    etz
    0.06
     stav
    0.06
    细胞
    0.06
    Act Density 0.005%

    No Known Activations