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

    Neuronpedia

    INDEX
    Explanations

    str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tn
    -0.07
    etections
    -0.07
     mv
    -0.06
    +'_
    -0.06
    uzey
    -0.06
     ohled
    -0.06
     tight
    -0.06
     competitor
    -0.06
    .oper
    -0.06
    ｛
    -0.06
    POSITIVE LOGITS
    repr
    0.07
     AH
    0.06
    REN
    0.06
    labels
    0.06
     환
    0.06
    (step
    0.06
    PK
    0.06
     chemical
    0.06
     DEF
    0.06
     indica
    0.06
    Act Density 0.001%

    No Known Activations