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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نین
    -0.07
     placement
    -0.07
    employees
    -0.07
     Tam
    -0.07
    sthrough
    -0.07
    "value
    -0.07
    combination
    -0.06
    θος
    -0.06
     srdce
    -0.06
    )application
    -0.06
    POSITIVE LOGITS
     what
    0.12
     WHAT
    0.10
    what
    0.08
     What
    0.08
    What
    0.08
    “What
    0.07
    .What
    0.07
     everything
    0.06
     �
    0.06
    ในป
    0.06
    Act Density 0.052%

    No Known Activations