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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     매매가
    -0.07
     Meh
    -0.07
    �
    -0.07
    orn
    -0.07
    rear
    -0.06
     ####
    -0.06
     tôn
    -0.06
    措
    -0.06
    .DataGridViewAutoSize
    -0.06
    @a
    -0.06
    POSITIVE LOGITS
     RADIO
    0.07
     endorsement
    0.07
     protection
    0.06
     Stretch
    0.06
     rocket
    0.06
     اصلاح
    0.06
     stacking
    0.06
    rl
    0.06
     shoved
    0.06
    カル
    0.06
    Act Density 0.529%

    No Known Activations