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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ової
    -0.07
     meds
    -0.07
     输入
    -0.07
     bathing
    -0.06
    covery
    -0.06
    -acre
    -0.06
    Needed
    -0.06
     Dictionary
    -0.06
     compressed
    -0.06
     Trace
    -0.06
    POSITIVE LOGITS
    aturday
    0.07
    vetica
    0.07
     DPR
    0.06
    -available
    0.06
    ˘
    0.06
    ´:
    0.06
    <Select
    0.06
     Hexatrigesimal
    0.06
     arrog
    0.06
     LaTeX
    0.06
    Act Density 0.028%

    No Known Activations