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

    Neuronpedia

    INDEX
    Explanations

    inter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    елів
    -0.06
     Unable
    -0.06
    etě
    -0.06
     Partition
    -0.06
    iever
    -0.06
    เกม
    -0.06
     nebude
    -0.06
    -action
    -0.06
    (INVOKE
    -0.06
    metis
    -0.06
    POSITIVE LOGITS
     Tol
    0.06
    ψε
    0.06
    /ac
    0.06
     조교
    0.06
     nk
    0.06
     Jerry
    0.06
    하
    0.06
    山
    0.06
    !=
    0.06
    )(↵
    0.06
    Act Density 0.015%

    No Known Activations