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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    优势
    -0.07
    Par
    -0.06
    orsch
    -0.06
    Reduc
    -0.06
     unsuccessfully
    -0.06
    해서
    -0.06
     hacer
    -0.06
     HV
    -0.06
     XMLHttpRequest
    -0.06
    Unfortunately
    -0.06
    POSITIVE LOGITS
    false
    0.07
    _ROOM
    0.07
    	Data
    0.06
    clide
    0.06
    _signature
    0.06
     '↵
    0.06
     потому
    0.06
    ews
    0.06
     соци
    0.06
     Dana
    0.06
    Act Density 0.001%

    No Known Activations