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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kü
    -0.08
    .mm
    -0.07
     cue
    -0.07
    -sized
    -0.07
    pedia
    -0.07
    EXPECT
    -0.07
    -‐
    -0.07
    ایان
    -0.06
    cmath
    -0.06
    viso
    -0.06
    POSITIVE LOGITS
     Jess
    0.06
     electric
    0.06
    ρώ
    0.06
    ULATE
    0.06
     ")"↵
    0.06
    лич
    0.06
     }];↵
    0.06
    TagName
    0.06
    Final
    0.06
     متفاوت
    0.06
    Act Density 0.001%

    No Known Activations