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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �다
    -0.06
    rying
    -0.06
    _trace
    -0.06
    _TIMESTAMP
    -0.06
    EATURE
    -0.06
    icers
    -0.06
    нил
    -0.06
    (phase
    -0.06
    read
    -0.06
     böyle
    -0.06
    POSITIVE LOGITS
    -overlay
    0.06
     '',
↵
    0.06
     supra
    0.06
    .'<
    0.06
     alın
    0.06
    Impro
    0.06
     mote
    0.06
     earned
    0.06
    (param
    0.06
     rukou
    0.05
    Act Density 0.016%

    No Known Activations