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

    Neuronpedia

    INDEX
    Explanations

    describing capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alt
    0.47
    Y
    0.47
    G
    0.46
    W
    0.46
    AT
    0.46
    Pour
    0.45
    YC
    0.44
    Al
    0.44
    EN
    0.44
    ARTA
    0.44
    POSITIVE LOGITS
     naïve
    0.60
     psychologically
    0.49
     microbiome
    0.49
     pressures
    0.49
     apocalyptic
    0.49
     ката
    0.48
     colorectal
    0.48
     множество
    0.48
     poultry
    0.47
     enveloped
    0.47
    Act Density 0.000%

    No Known Activations