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

    Neuronpedia

    INDEX
    Explanations

    rare events over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Train
    -0.07
    iever
    -0.07
    estr
    -0.06
    pipe
    -0.06
    _Com
    -0.06
     Ava
    -0.06
    _SUBJECT
    -0.06
     Ike
    -0.06
     코
    -0.05
    jím
    -0.05
    POSITIVE LOGITS
    (objects
    0.07
    (tasks
    0.07
     uri
    0.07
    __(↵
    0.07
     metall
    0.07
    CLUDING
    0.06
    уч
    0.06
    ('/');↵
    0.06
     workflows
    0.06
     semi
    0.06
    Act Density 0.003%

    No Known Activations