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

    Neuronpedia

    INDEX
    Explanations

    Horror films

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    931
    -0.07
    901
    -0.07
    Thr
    -0.06
    _defined
    -0.06
    506
    -0.06
     Queue
    -0.06
    698
    -0.06
    pp
    -0.06
    806
    -0.06
    สะดวก
    -0.06
    POSITIVE LOGITS
    ")==
    0.07
    .ToolStripMenuItem
    0.07
     Characters
    0.07
    /mat
    0.06
     Cros
    0.06
    paste
    0.06
     happened
    0.06
     distur
    0.06
    >false
    0.06
    ">*</
    0.06
    Act Density 0.012%

    No Known Activations