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

    Neuronpedia

    INDEX
    Explanations

    Fs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fs
    -0.94
     fs
    -0.79
    FS
    -0.75
     prefer
    -0.74
    Fs
    -0.74
    ore
    -0.73
    length
    -0.54
     Want
    -0.49
     Bre
    -0.48
     need
    -0.48
    POSITIVE LOGITS
     Efq
    1.01
     Jefus
    0.88
     pleaſure
    0.85
     itſelf
    0.85
     myſelf
    0.82
     purpoſe
    0.81
     Theſe
    0.81
     whoſe
    0.80
     Monfieur
    0.79
     himſelf
    0.77
    Act Density 1.246%

    No Known Activations