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

    Neuronpedia

    INDEX
    Explanations

    haunted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جو
    -0.07
     triples
    -0.07
     rf
    -0.07
    duplicate
    -0.07
     позитив
    -0.07
     midfielder
    -0.07
    �
    -0.07
     wires
    -0.06
     posit
    -0.06
     σημαν
    -0.06
    POSITIVE LOGITS
    وید
    0.07
    OSC
    0.07
     hacker
    0.07
    	dx
    0.06
     روح
    0.06
     _↵↵
    0.06
    Haunted
    0.06
     ")↵↵
    0.06
    TY
    0.06
    žit
    0.06
    Act Density 0.004%

    No Known Activations