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

    Neuronpedia

    INDEX
    Explanations

    dip and diploma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sleep
    0.51
     Mart
    0.47
     Tall
    0.46
    amu
    0.45
     MART
    0.43
    b
    0.43
     przesz
    0.42
    pid
    0.42
    我对
    0.42
     चला
    0.42
    POSITIVE LOGITS
     dipped
    0.99
    Dip
    0.96
     dipping
    0.89
     Dip
    0.88
     dip
    0.88
     dips
    0.81
    蘸
    0.81
    Dipl
    0.79
    dip
    0.76
     dipole
    0.76
    Act Density 0.007%

    No Known Activations