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

    Neuronpedia

    INDEX
    Explanations

    permission/allowance

    np_max-act · gemini-2.0-flash

    arguments related to negative experiences and dissatisfaction with systems or structures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     дж
    -0.07
    pedido
    -0.07
    .enter
    -0.06
     collaps
    -0.06
     svm
    -0.06
     полот
    -0.06
    _ph
    -0.06
     feu
    -0.06
     проз
    -0.06
     terrified
    -0.06
    POSITIVE LOGITS
    ->{$
    0.07
    }/#{
    0.06
    .*(
    0.06
     homelessness
    0.06
     якості
    0.06
    /go
    0.06
    โปรแกรม
    0.06
     буду
    0.06
    ί
    0.06
     contrace
    0.06
    Act Density 0.120%

    No Known Activations