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

    Neuronpedia

    INDEX
    Explanations

    immunocompromised

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Author
    -0.07
    .Type
    -0.06
    _resource
    -0.06
     charm
    -0.06
    َو
    -0.06
    IH
    -0.06
    ψε
    -0.06
    unifu
    -0.06
    _shutdown
    -0.06
     استر
    -0.06
    POSITIVE LOGITS
     kans
    0.06
     slut
    0.06
    (nd
    0.06
     بأن
    0.06
     Wrestling
    0.06
    ################################################################################
    0.06
    .calls
    0.06
     ninh
    0.06
     blackout
    0.06
    AllArgsConstructor
    0.06
    Act Density 0.037%

    No Known Activations