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

    Neuronpedia

    INDEX
    Explanations

    horror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    фт
    -0.06
    _na
    -0.06
     Lindsay
    -0.06
    _predict
    -0.06
     mez
    -0.06
     isValid
    -0.06
     deque
    -0.06
    />";↵
    -0.06
    *@
    -0.06
     Tank
    -0.06
    POSITIVE LOGITS
     horror
    0.13
     Horror
    0.13
     horrors
    0.11
     Hor
    0.08
     terror
    0.08
     Fury
    0.07
    94
    0.07
     Cry
    0.07
    ro
    0.07
    hell
    0.07
    Act Density 0.005%

    No Known Activations