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

    Neuronpedia

    INDEX
    Explanations

    words related to tips in different settings whether it be the 'tip' of something like an arm or instructions on how to do something

    oai_token-act-pair · gemini-2.0-flash

    tip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tip
    -3.16
     Tip
    -3.05
     tips
    -3.02
    Tip
    -2.88
    tip
    -2.70
    tips
    -2.69
     TIP
    -2.63
     Tips
    -2.61
    Tips
    -2.56
    TIP
    -2.44
    POSITIVE LOGITS
    emény
    0.51
     matières
    0.47
    ıştır
    0.46
    miljø
    0.46
    Appellee
    0.45
     chay
    0.44
     dimensionality
    0.44
    crimination
    0.44
    chinen
    0.44
    jutnya
    0.43
    Act Density 1.798%

    No Known Activations