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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handshake
    -0.08
    Nak
    -0.07
    innan
    -0.07
    .NONE
    -0.07
    .confirm
    -0.07
     hold
    -0.07
    #create
    -0.07
     confirmation
    -0.07
    .Hand
    -0.07
     Burn
    -0.07
    POSITIVE LOGITS
     lows
    0.11
    PARATOR
    0.08
     altamente
    0.08
     mengalami
    0.08
     către
    0.08
    Comparable
    0.08
     laŭ
    0.08
     escaped
    0.08
     प्रमुख
    0.08
     prioritized
    0.07
    Act Density 0.054%

    No Known Activations