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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squared
    -0.08
     towards
    -0.07
    рип
    -0.07
    _BUFF
    -0.07
    openssl
    -0.07
    초
    -0.07
    depends
    -0.07
     quoting
    -0.06
     sweets
    -0.06
    owards
    -0.06
    POSITIVE LOGITS
    ]
    0.07
     kidney
    0.06
    PTY
    0.06
    물
    0.06
     that
    0.06
    who
    0.06
     mutations
    0.06
    bred
    0.06
    (kv
    0.06
     KA
    0.06
    Act Density 0.021%

    No Known Activations