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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dto
    -0.06
    'H
    -0.06
    ose
    -0.06
    /rec
    -0.06
    ASC
    -0.06
     oft
    -0.06
    Ｉ
    -0.06
    /reg
    -0.06
    ῶν
    -0.06
    श
    -0.06
    POSITIVE LOGITS
     hut
    0.07
    	control
    0.07
     sponsored
    0.07
    mít
    0.07
     ceramic
    0.07
     ceramics
    0.06
    .delay
    0.06
     cropping
    0.06
     neat
    0.06
     convo
    0.06
    Act Density 0.057%

    No Known Activations