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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cristina
    -0.07
     Midlands
    -0.06
    detach
    -0.06
     consulate
    -0.06
     Miner
    -0.06
    .iso
    -0.06
     Tacoma
    -0.06
    νου
    -0.06
    신청
    -0.06
     поможет
    -0.06
    POSITIVE LOGITS
    testing
    0.07
    ")))↵
    0.06
     MA
    0.06
     asla
    0.06
    leave
    0.06
    	char
    0.06
     comment
    0.06
    №
    0.06
    mann
    0.06
    roma
    0.06
    Act Density 0.018%

    No Known Activations