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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vi
    -0.07
     impossible
    -0.07
     ref
    -0.06
     مقد
    -0.06
     NONINFRINGEMENT
    -0.06
     آورد
    -0.06
     Council
    -0.06
     reimburse
    -0.06
    VO
    -0.06
    Flow
    -0.06
    POSITIVE LOGITS
    อเร
    0.08
    侍
    0.07
    _ac
    0.07
    dfs
    0.07
     прест
    0.06
    _ax
    0.06
    .salary
    0.06
     ATM
    0.06
    Tonight
    0.06
    .process
    0.06
    Act Density 0.028%

    No Known Activations