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

    Neuronpedia

    INDEX
    Explanations

    statements and viewpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WW
    -0.07
     března
    -0.06
    불
    -0.06
     đây
    -0.06
    	x
    -0.06
     GP
    -0.06
    Query
    -0.06
    PLAY
    -0.06
    763
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     reinstall
    0.07
     kims
    0.07
     prac
    0.07
    _rnn
    0.07
    jíž
    0.07
     tốt
    0.07
    CLEAR
    0.07
     emphasize
    0.06
    乃
    0.06
    /mit
    0.06
    Act Density 0.050%

    No Known Activations