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

    Neuronpedia

    INDEX
    Explanations

    struggle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plays
    -0.06
    ooting
    -0.06
    ermo
    -0.06
    upt
    -0.06
     Lowest
    -0.06
    Crear
    -0.06
     KS
    -0.06
    PIP
    -0.06
    unned
    -0.06
     concent
    -0.06
    POSITIVE LOGITS
     heroin
    0.07
     Dil
    0.07
     insignificant
    0.07
     NUITKA
    0.07
     arrivals
    0.07
     Wag
    0.07
     zeigt
    0.07
    destruct
    0.06
    Quaternion
    0.06
    运动
    0.06
    Act Density 0.011%

    No Known Activations