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

    Neuronpedia

    INDEX
    Explanations

    javascript sdk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tow
    -0.07
    cas
    -0.07
     Amph
    -0.07
    .hide
    -0.07
    ima
    -0.06
     mentioned
    -0.06
    rough
    -0.06
    arie
    -0.06
    space
    -0.06
    Camp
    -0.06
    POSITIVE LOGITS
     четыре
    0.08
    תחושה
    0.07
     climates
    0.07
     subst
    0.07
    忧
    0.07
     diz
    0.07
     granny
    0.07
    先把
    0.07
    -blocking
    0.07
     predictor
    0.07
    Act Density 0.001%

    No Known Activations