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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]?.
    -0.07
    Ts
    -0.06
     callers
    -0.06
     Cres
    -0.06
    foobar
    -0.06
     Saras
    -0.06
     баб
    -0.06
     Grandma
    -0.06
    μή
    -0.06
    Depth
    -0.06
    POSITIVE LOGITS
    086
    0.07
    :(
    0.07
    _finished
    0.07
     hue
    0.07
     }}↵
    0.06
    ники
    0.06
    (Boolean
    0.06
    .renderer
    0.06
     ella
    0.06
    _CHANGED
    0.06
    Act Density 0.047%

    No Known Activations