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

    Neuronpedia

    INDEX
    Explanations

    absorption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uite
    -0.08
     tree
    -0.08
     planet
    -0.08
    QUARE
    -0.07
     Tree
    -0.07
     trail
    -0.07
     Lia
    -0.07
    Tuesday
    -0.07
    _tree
    -0.07
    CommandEvent
    -0.07
    POSITIVE LOGITS
     absorb
    0.11
     absorption
    0.10
     absorbs
    0.09
     ABS
    0.09
    -abs
    0.09
     Abs
    0.09
     absorbed
    0.09
    abs
    0.09
    ABS
    0.09
     absorbing
    0.09
    Act Density 0.014%

    No Known Activations