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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vere
    -0.07
    xce
    -0.07
    _patches
    -0.06
    heat
    -0.06
    igator
    -0.06
    erse
    -0.06
     ges
    -0.06
    pest
    -0.06
    Fe
    -0.06
     fres
    -0.06
    POSITIVE LOGITS
    U
    0.09
    u
    0.08
    y
    0.08
    0.08
    и
    0.08
     unl
    0.08
    I
    0.08
    い
    0.07
    uh
    0.07
     un
    0.07
    Act Density 0.040%

    No Known Activations