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

    Neuronpedia

    INDEX
    Explanations

    certain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    support
    -0.07
     apex
    -0.06
     取
    -0.06
     Egyptians
    -0.06
    Skill
    -0.06
    etypes
    -0.06
     triggered
    -0.06
     threats
    -0.06
     sol
    -0.06
     Jac
    -0.06
    POSITIVE LOGITS
    xia
    0.07
    .limit
    0.06
     Calif
    0.06
    ظ
    0.06
    (Temp
    0.06
     Его
    0.06
     performs
    0.06
    icie
    0.06
    žení
    0.06
     категор
    0.06
    Act Density 0.010%

    No Known Activations