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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    供暖
    -0.07
    -0.07
    望
    -0.07
    rists
    -0.07
    .tar
    -0.07
    媛
    -0.07
     stringWith
    -0.06
    VIOUS
    -0.06
    xAC
    -0.06
     hysteria
    -0.06
    POSITIVE LOGITS
    eat
    0.07
    runtime
    0.07
    addons
    0.07
    uru
    0.07
     defeating
    0.07
    _secs
    0.07
    schüt
    0.07
     Meta
    0.07
    _STEP
    0.07
    ADED
    0.07
    Act Density 0.173%

    No Known Activations