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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    /control
    -0.07
    ons
    -0.07
     stressing
    -0.07
    っき
    -0.07
    stoff
    -0.07
    蚤
    -0.07
     surroundings
    -0.07
     boasting
    -0.07
     penis
    -0.06
    POSITIVE LOGITS
    Syn
    0.07
    !)↵
    0.07
     Howard
    0.07
     Lou
    0.07
     Braz
    0.07
    ϑ
    0.07
     Kirk
    0.07
    .dat
    0.07
    System
    0.07
    %");↵
    0.07
    Act Density 0.043%

    No Known Activations