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

    Neuronpedia

    INDEX
    Explanations

    related to scientists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Introduced
    -0.07
     dlou
    -0.07
    _Entry
    -0.07
     yanı
    -0.06
    Fallback
    -0.06
    ofile
    -0.06
     HOWEVER
    -0.06
    nw
    -0.06
    	uint
    -0.06
    .student
    -0.06
    POSITIVE LOGITS
     concentrations
    0.07
     contaminated
    0.07
     scram
    0.07
     CLL
    0.06
     oldu
    0.06
     congratulate
    0.06
     Steven
    0.06
     formulation
    0.06
     inventor
    0.06
     cheering
    0.06
    Act Density 0.028%

    No Known Activations