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

    Neuronpedia

    INDEX
    Explanations

    births

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spins
    -0.07
     eating
    -0.07
    итив
    -0.07
    spm
    -0.06
    large
    -0.06
    iddle
    -0.06
    tep
    -0.06
    Info
    -0.06
    lığın
    -0.06
     اق
    -0.06
    POSITIVE LOGITS
    	RTCT
    0.07
    0.07
    _rom
    0.06
     ToolStrip
    0.06
    _Tick
    0.06
    0.06
     花
    0.06
    _priv
    0.06
     erotische
    0.06
    _FORWARD
    0.06
    Act Density 0.005%

    No Known Activations