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

    Neuronpedia

    INDEX
    Explanations

    balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STREET
    -0.07
    ("'
    -0.07
     torn
    -0.07
    面积
    -0.07
    _saida
    -0.07
     momentum
    -0.07
    	tests
    -0.07
    莉
    -0.07
    tement
    -0.07
    ัฒน
    -0.06
    POSITIVE LOGITS
     chan
    0.07
     redundant
    0.06
     dq
    0.06
    Navigate
    0.06
    bab
    0.06
    092
    0.06
     executed
    0.06
     compensate
    0.05
     alleg
    0.05
    390
    0.05
    Act Density 0.006%

    No Known Activations