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

    Neuronpedia

    INDEX
    Explanations

    passages describing ice cream

    oai_token-act-pair · gemini-2.0-flash

    ice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -0.63
     otomatig
    -0.60
    ########.
    -0.55
    RectangleBorder
    -0.54
    anyahu
    -0.52
    mybatisplus
    -0.50
    __':
    -0.49
    BufferException
    -0.49
     disponibilités
    -0.48
    esModule
    -0.48
    POSITIVE LOGITS
     littéraire
    0.54
     estimés
    0.52
     cse
    0.52
     expéri
    0.51
    ceton
    0.50
     Shaksp
    0.49
    ade
    0.49
    kins
    0.49
    خة
    0.48
    هران
    0.48
    Act Density 2.834%

    No Known Activations