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

    Neuronpedia

    INDEX
    Explanations

    US Navy ships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    应该是
    -0.07
    リ
    -0.07
    ショー
    -0.07
    reflect
    -0.07
    㢨
    -0.07
    uncture
    -0.06
    inging
    -0.06
    જ
    -0.06
     Advocate
    -0.06
    .glide
    -0.06
    POSITIVE LOGITS
    Gran
    0.08
     PWM
    0.07
     ';↵↵
    0.07
    ⏫
    0.07
    �
    0.07
     poz
    0.07
    ButtonDown
    0.07
     AABB
    0.07
     instit
    0.07
    Dialog
    0.07
    Act Density 0.039%

    No Known Activations