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

    Neuronpedia

    INDEX
    Explanations

    strength level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eer
    -0.10
    TRL
    -0.10
    ãģĬãĤĬ
    -0.10
    pras
    -0.10
    gest
    -0.10
    ally
    -0.09
    rame
    -0.09
    erken
    -0.09
    abee
    -0.09
    StateChanged
    -0.09
    POSITIVE LOGITS
     mẽ
    0.22
    ener
    0.20
    holds
    0.18
    ening
    0.17
    NGTH
    0.16
    ens
    0.14
    eners
    0.13
    ened
    0.13
    sville
    0.12
    fully
    0.12
    Act Density 0.027%

    No Known Activations