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

    Neuronpedia

    INDEX
    Explanations

    death, ending, negative events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     повыш
    -0.08
     koy
    -0.07
     ép
    -0.07
    Seven
    -0.07
    uş
    -0.06
    粒
    -0.06
     enf
    -0.06
     valeurs
    -0.06
    �
    -0.06
     arrows
    -0.06
    POSITIVE LOGITS
    LEM
    0.06
    182
    0.06
     ー
    0.06
     Border
    0.06
     DIFF
    0.06
    _WAIT
    0.05
    -performance
    0.05
    lem
    0.05
     Faith
    0.05
    __↵
    0.05
    Act Density 0.084%

    No Known Activations