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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ICY
    -0.29
    <decltype
    -0.27
     assaulting
    -0.25
     [[]
    -0.24
    PTY
    -0.24
     bites
    -0.24
    _ax
    -0.24
    éĢĨ
    -0.23
    /mobile
    -0.23
     bite
    -0.23
    POSITIVE LOGITS
     surplus
    0.28
     push
    0.28
    utan
    0.28
     Pepper
    0.27
     picking
    0.27
     pick
    0.27
    asper
    0.26
    spell
    0.26
    immer
    0.26
     picks
    0.25
    Act Density 0.044%

    No Known Activations