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

    Neuronpedia

    INDEX
    Explanations

    however

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    훈
    -0.07
    >↵↵↵↵↵
    -0.07
    利
    -0.06
    .cid
    -0.06
    assa
    -0.06
    etleri
    -0.06
    stops
    -0.06
    alker
    -0.06
     Berlin
    -0.06
    ,len
    -0.06
    POSITIVE LOGITS
     Thor
    0.07
     Ent
    0.06
    precedented
    0.06
     آر
    0.06
     flea
    0.06
    .Symbol
    0.06
     економ
    0.06
     MMP
    0.06
     Tcl
    0.06
    SECOND
    0.06
    Act Density 0.005%

    No Known Activations