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

    Neuronpedia

    INDEX
    Explanations

    Seconds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HI
    -0.07
    Susan
    -0.07
    לס
    -0.07
    ailand
    -0.07
    nostic
    -0.07
    藓
    -0.07
    izations
    -0.07
    outfile
    -0.07
    lication
    -0.07
    .,↵
    -0.07
    POSITIVE LOGITS
    .Type
    0.09
     perpetrators
    0.07
     Ergebn
    0.07
    _PRED
    0.07
     удар
    0.07
     благодар
    0.07
     Joined
    0.07
    .Target
    0.07
    _From
    0.07
    .Manager
    0.07
    Act Density 0.004%

    No Known Activations