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

    Neuronpedia

    INDEX
    Explanations

    stabbing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     myſelf
    -0.89
     Shakspeare
    -0.84
     Efq
    -0.83
     سكانية
    -0.81
    =$?
    -0.80
    esModule
    -0.78
     Shaksp
    -0.76
     themſelves
    -0.75
     himſelf
    -0.74
    POSITIVE LOGITS
    arg
    0.47
    be
    0.45
    imp
    0.42
     verlo
    0.42
    mer
    0.41
    er
    0.40
    pe
    0.40
    hk
    0.40
    providedIn
    0.40
    ce
    0.40
    Act Density 0.093%

    No Known Activations