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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -d
    -0.06
    .codec
    -0.06
    男人
    -0.06
     земли
    -0.06
    ZO
    -0.06
    agner
    -0.06
     EDT
    -0.06
    ,len
    -0.06
     prayers
    -0.06
    ymous
    -0.06
    POSITIVE LOGITS
     Clock
    0.07
    _()↵
    0.06
    gateway
    0.06
    (md
    0.06
    strings
    0.06
    -rounded
    0.06
    eless
    0.06
    ReceiveProps
    0.05
    hey
    0.05
     superb
    0.05
    Act Density 0.022%

    No Known Activations