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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EFF
    -0.07
     objet
    -0.07
     oft
    -0.07
     Stark
    -0.07
    чих
    -0.07
     craftsm
    -0.07
    strand
    -0.07
     ();
↵
    -0.06
     Welt
    -0.06
    蓝
    -0.06
    POSITIVE LOGITS
     no
    0.19
     No
    0.18
    No
    0.16
    no
    0.16
    -no
    0.15
     NO
    0.15
    NO
    0.14
    .No
    0.14
    .no
    0.14
    "No
    0.13
    Act Density 0.108%

    No Known Activations