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

    Neuronpedia

    INDEX
    Explanations

    phrases related to engagement and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thank you for attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.51
     tartalomajánló
    -0.50
     InputDecoration
    -0.49
     acceptez
    -0.47
    })->
    -0.47
     zijne
    -0.46
     validamos
    -0.46
     ſal
    -0.46
    },{
    -0.45
     deſt
    -0.45
    POSITIVE LOGITS
    fullscreen
    0.41
     astore
    0.40
     Paving
    0.40
     digress
    0.39
    cia
    0.39
    WriteBarrier
    0.38
    GrantedAuthority
    0.38
     ating
    0.38
     Piping
    0.37
    imread
    0.37
    Act Density 0.010%

    No Known Activations