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

    Neuronpedia

    INDEX
    Explanations

    arrests and warrants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aside
    -0.08
     Assumes
    -0.07
    ISION
    -0.07
    Ὑ
    -0.07
    ASM
    -0.07
    �
    -0.07
    crc
    -0.07
    ARDS
    -0.07
    谿
    -0.07
    だけど
    -0.07
    POSITIVE LOGITS
    /web
    0.07
    (container
    0.07
     target
    0.07
    .brand
    0.06
     bod
    0.06
     &=
    0.06
    :",
    0.06
    andidates
    0.06
     ",
    0.06
    ead
    0.06
    Act Density 0.060%

    No Known Activations